In recent years, deep learning has achieved great success in the field of image processing. In the single image super-resolution (SISR) task, the convolutional neural network (CNN) extracts the features of the image through deeper layers, and has achieved impressive results. In this paper, we propose a single image super-resolution model based on Adaptive Deep Residual named as ADR-SR, which uses the Input Output Same Size (IOSS) structure, and releases the dependence of upsampling layers compared with the existing SR methods. Specifically, the key element of our model is the Adaptive Residual Block (ARB), which replaces the commonly used constant factor with an adaptive residual factor. The experiments prove the effectiveness of our ADR-SR model, which can not only reconstruct images with better visual effects, but also get better objective performances.

中文翻译：

---

用于单图像超分辨率的自适应深度残差网络

近年来，深度学习在图像处理领域取得了巨大的成功。在单图像超分辨率（SISR）任务中，卷积神经网络（CNN）通过更深的层提取图像的特征，并取得了令人印象深刻的结果。在本文中，我们提出了一种基于自适应深度残差的单图像超分辨率模型，称为ADR-SR，它使用输入输出相同大小（IOSS）结构，并且与现有的SR方法相比，释放了上采样层的依赖性。具体来说，我们模型的关键要素是自适应残差块（ARB），它用自适应残差因子代替了常用的常数因子。实验证明了我们的ADR-SR模型的有效性，该模型不仅可以重建具有更好视觉效果的图像，